DS

D. Sochirca

2 records found

Appearance-based 3D gaze estimation must accommodate two conflicting needs: fine ocular detail and global facial context. Vanilla Vision Transformers (ViTs) struggle with both needs due to their fixed 16 × 16 patch grid that (i) fragments critical features like the eyes into mult ...

Compressing code generation language models on CPUs

Using Group Lasso pruning and post-training quantization

Code generation models have become more popular recently, due to the fact that they assist developers in writing code in a more productive manner. While these large models deliver impressive performance, they require significant computational resources and memory, making them dif ...